大模型推理案头手册（开源版）：给定 GPU 算力，一个模型能扛多少 QPS？三层模型 × 三面墙 × 排队论 × 开环压测
☆50Sep 2, 2026Updated this week
Alternatives and similar repositories for llm-inference-capacity-handbook
Users that are interested in llm-inference-capacity-handbook are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 栖言（Qiyan）是一款本地优先的 Windows AI 桌面工作台，支持 BYOK、多模型配置、AI 聊天、灵感笔记、哄哄模拟器与 ChatPDF 文档问答。☆17Jul 14, 2026Updated last month
- 基于 Jingyun Studio + DeepSeek Harness (DSH) 打造的一站式 AI 商业化桌面客户端☆13Updated this week
- Hub for Just-DDL topic repositories and future mini program/app surfaces☆24Jun 18, 2026Updated 2 months ago
- a super agent in web☆28Jun 5, 2026Updated 2 months ago
- [ICML 2026] DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling☆36Jun 8, 2026Updated 2 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Enhanced GenericAgent with parallel execution and vector memory☆68Mar 9, 2026Updated 5 months ago
- Creating custom widgets on your Mac desktop.☆90Jun 18, 2026Updated 2 months ago
- ☆47May 22, 2026Updated 3 months ago
- Let AI agents design with you.☆54May 13, 2026Updated 3 months ago
- 股票、期货实时数据与模拟盘自动化公开演示版☆100Mar 26, 2026Updated 5 months ago
- An example smart contract + test suite for communicating over IBC.☆14Oct 27, 2025Updated 10 months ago
- Two image models for face expression recognition and for ethnic classification☆15Oct 27, 2025Updated 10 months ago
- Personal GitHub Pages site for owenscatherinexuv-28☆12Sep 9, 2025Updated 11 months ago
- PMS-RAG algorithm for diabetes☆53Apr 19, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- 基于垂直领域微调模型的交互式国风文化创作平台☆33Jun 21, 2026Updated 2 months ago
- DeepTime Sauropsida：交互式蜥形纲演化树，3D 螺旋序幕 + D3.js 动态时间树，跨越 3 亿年 | Interactive sauropsid phylogeny with 3D spiral intro & D3.js dynamic timetr…☆20Aug 8, 2026Updated 3 weeks ago
- Truffle, Webpack, React, Redux boilerplate with routing and authentication via a smart contract.☆15Oct 27, 2025Updated 10 months ago
- understandingethereumtrie=================☆15Oct 27, 2025Updated 10 months ago
- Cross-platform application with intuitive user interface☆15Oct 27, 2025Updated 10 months ago
- The fastest oracle on Solana☆14Oct 27, 2025Updated 10 months ago
- A distributed system for detecting vulnerabilities in smart contracts using Docker, gRPC, RabbitMQ, Redis, MySQL, and Nginx.☆13Oct 27, 2025Updated 10 months ago
- ☆18Jul 20, 2026Updated last month
- EOSIO & EVM smart contract unit testing suite and API provider☆15Oct 27, 2025Updated 10 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Scalable architecture for enterprise-level applications☆16Oct 27, 2025Updated 10 months ago
- Troubleshooting skills for Alibaba Cloud ECS☆147Aug 20, 2026Updated 2 weeks ago
- ☆366Jul 20, 2026Updated last month
- Next-generation UI automation harness powered by Python & Playwright. Chat with AI Agents to seamlessly generate, architect, and execute …☆157May 24, 2026Updated 3 months ago
- A developer-friendly, rollup-based Ethereum Layer 2 solution that offers low fees and EVM equivalence.☆17Oct 27, 2025Updated 10 months ago
- A modern web application built with cutting-edge technologies☆18Oct 27, 2025Updated 10 months ago
- Advanced Burp Suite Logging Extension☆15Oct 27, 2025Updated 10 months ago
- <div align='center'> EthosA collection☆16Oct 27, 2025Updated 10 months ago
- AmbiVer: 3D Instruction Ambiguity Detection Official code for 3D Instruction Ambiguity Detection (arXiv:2601.05991).☆26Aug 1, 2026Updated last month
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Decentralized and light Ethereum Wallet☆14Oct 27, 2025Updated 10 months ago
- Compares frontend project bundles☆15Oct 27, 2025Updated 10 months ago
- Harness is an AI Agent development guardrail Meta-Skill that establishes four layers of defense for any project in one command: knowledge…☆265May 4, 2026Updated 4 months ago
- AI-powered automated code repair agent — Bug Location → Patch Generation → Test Verification → Safety Review, powered by LangGraph + LLM☆21Jul 2, 2026Updated 2 months ago
- World building for everyone☆16Oct 27, 2025Updated 10 months ago
- Web-based ROI and lane annotation review tool for AAT image datasets.☆22May 28, 2026Updated 3 months ago
- A modern web application built with cutting-edge technologies☆15Oct 27, 2025Updated 10 months ago